Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 714 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c
new file mode 100644
index 000000000..f43cce16b
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c
@@ -0,0 +1,714 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+/*
+ * dc_helper.c
+ *
+ *  Created on: Aug 30, 2016
+ *      Author: agrodzov
+ */
+
+#include <linux/delay.h>
+#include <linux/stdarg.h>
+
+#include "dm_services.h"
+
+#include "dc.h"
+#include "dc_dmub_srv.h"
+#include "reg_helper.h"
+
+static inline void submit_dmub_read_modify_write(
+	struct dc_reg_helper_state *offload,
+	const struct dc_context *ctx)
+{
+	struct dmub_rb_cmd_read_modify_write *cmd_buf = &offload->cmd_data.read_modify_write;
+	bool gather = false;
+
+	offload->should_burst_write =
+			(offload->same_addr_count == (DMUB_READ_MODIFY_WRITE_SEQ__MAX - 1));
+	cmd_buf->header.payload_bytes =
+			sizeof(struct dmub_cmd_read_modify_write_sequence) * offload->reg_seq_count;
+
+	gather = ctx->dmub_srv->reg_helper_offload.gather_in_progress;
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = false;
+
+	dc_dmub_srv_cmd_queue(ctx->dmub_srv, &offload->cmd_data);
+
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = gather;
+
+	memset(cmd_buf, 0, sizeof(*cmd_buf));
+
+	offload->reg_seq_count = 0;
+	offload->same_addr_count = 0;
+}
+
+static inline void submit_dmub_burst_write(
+	struct dc_reg_helper_state *offload,
+	const struct dc_context *ctx)
+{
+	struct dmub_rb_cmd_burst_write *cmd_buf = &offload->cmd_data.burst_write;
+	bool gather = false;
+
+	cmd_buf->header.payload_bytes =
+			sizeof(uint32_t) * offload->reg_seq_count;
+
+	gather = ctx->dmub_srv->reg_helper_offload.gather_in_progress;
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = false;
+
+	dc_dmub_srv_cmd_queue(ctx->dmub_srv, &offload->cmd_data);
+
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = gather;
+
+	memset(cmd_buf, 0, sizeof(*cmd_buf));
+
+	offload->reg_seq_count = 0;
+}
+
+static inline void submit_dmub_reg_wait(
+		struct dc_reg_helper_state *offload,
+		const struct dc_context *ctx)
+{
+	struct dmub_rb_cmd_reg_wait *cmd_buf = &offload->cmd_data.reg_wait;
+	bool gather = false;
+
+	gather = ctx->dmub_srv->reg_helper_offload.gather_in_progress;
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = false;
+
+	dc_dmub_srv_cmd_queue(ctx->dmub_srv, &offload->cmd_data);
+
+	memset(cmd_buf, 0, sizeof(*cmd_buf));
+	offload->reg_seq_count = 0;
+
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = gather;
+}
+
+struct dc_reg_value_masks {
+	uint32_t value;
+	uint32_t mask;
+};
+
+struct dc_reg_sequence {
+	uint32_t addr;
+	struct dc_reg_value_masks value_masks;
+};
+
+static inline void set_reg_field_value_masks(
+	struct dc_reg_value_masks *field_value_mask,
+	uint32_t value,
+	uint32_t mask,
+	uint8_t shift)
+{
+	ASSERT(mask != 0);
+
+	field_value_mask->value = (field_value_mask->value & ~mask) | (mask & (value << shift));
+	field_value_mask->mask = field_value_mask->mask | mask;
+}
+
+static void set_reg_field_values(struct dc_reg_value_masks *field_value_mask,
+		uint32_t addr, int n,
+		uint8_t shift1, uint32_t mask1, uint32_t field_value1,
+		va_list ap)
+{
+	uint32_t shift, mask, field_value;
+	int i = 1;
+
+	/* gather all bits value/mask getting updated in this register */
+	set_reg_field_value_masks(field_value_mask,
+			field_value1, mask1, shift1);
+
+	while (i < n) {
+		shift = va_arg(ap, uint32_t);
+		mask = va_arg(ap, uint32_t);
+		field_value = va_arg(ap, uint32_t);
+
+		set_reg_field_value_masks(field_value_mask,
+				field_value, mask, shift);
+		i++;
+	}
+}
+
+static void dmub_flush_buffer_execute(
+		struct dc_reg_helper_state *offload,
+		const struct dc_context *ctx)
+{
+	submit_dmub_read_modify_write(offload, ctx);
+	dc_dmub_srv_cmd_execute(ctx->dmub_srv);
+}
+
+static void dmub_flush_burst_write_buffer_execute(
+		struct dc_reg_helper_state *offload,
+		const struct dc_context *ctx)
+{
+	submit_dmub_burst_write(offload, ctx);
+	dc_dmub_srv_cmd_execute(ctx->dmub_srv);
+}
+
+static bool dmub_reg_value_burst_set_pack(const struct dc_context *ctx, uint32_t addr,
+		uint32_t reg_val)
+{
+	struct dc_reg_helper_state *offload = &ctx->dmub_srv->reg_helper_offload;
+	struct dmub_rb_cmd_burst_write *cmd_buf = &offload->cmd_data.burst_write;
+
+	/* flush command if buffer is full */
+	if (offload->reg_seq_count == DMUB_BURST_WRITE_VALUES__MAX)
+		dmub_flush_burst_write_buffer_execute(offload, ctx);
+
+	if (offload->cmd_data.cmd_common.header.type == DMUB_CMD__REG_SEQ_BURST_WRITE &&
+			addr != cmd_buf->addr) {
+		dmub_flush_burst_write_buffer_execute(offload, ctx);
+		return false;
+	}
+
+	cmd_buf->header.type = DMUB_CMD__REG_SEQ_BURST_WRITE;
+	cmd_buf->header.sub_type = 0;
+	cmd_buf->addr = addr;
+	cmd_buf->write_values[offload->reg_seq_count] = reg_val;
+	offload->reg_seq_count++;
+
+	return true;
+}
+
+static uint32_t dmub_reg_value_pack(const struct dc_context *ctx, uint32_t addr,
+		struct dc_reg_value_masks *field_value_mask)
+{
+	struct dc_reg_helper_state *offload = &ctx->dmub_srv->reg_helper_offload;
+	struct dmub_rb_cmd_read_modify_write *cmd_buf = &offload->cmd_data.read_modify_write;
+	struct dmub_cmd_read_modify_write_sequence *seq;
+
+	/* flush command if buffer is full */
+	if (offload->cmd_data.cmd_common.header.type != DMUB_CMD__REG_SEQ_BURST_WRITE &&
+			offload->reg_seq_count == DMUB_READ_MODIFY_WRITE_SEQ__MAX)
+		dmub_flush_buffer_execute(offload, ctx);
+
+	if (offload->should_burst_write) {
+		if (dmub_reg_value_burst_set_pack(ctx, addr, field_value_mask->value))
+			return field_value_mask->value;
+		else
+			offload->should_burst_write = false;
+	}
+
+	/* pack commands */
+	cmd_buf->header.type = DMUB_CMD__REG_SEQ_READ_MODIFY_WRITE;
+	cmd_buf->header.sub_type = 0;
+	seq = &cmd_buf->seq[offload->reg_seq_count];
+
+	if (offload->reg_seq_count) {
+		if (cmd_buf->seq[offload->reg_seq_count - 1].addr == addr)
+			offload->same_addr_count++;
+		else
+			offload->same_addr_count = 0;
+	}
+
+	seq->addr = addr;
+	seq->modify_mask = field_value_mask->mask;
+	seq->modify_value = field_value_mask->value;
+	offload->reg_seq_count++;
+
+	return field_value_mask->value;
+}
+
+static void dmub_reg_wait_done_pack(const struct dc_context *ctx, uint32_t addr,
+		uint32_t mask, uint32_t shift, uint32_t condition_value, uint32_t time_out_us)
+{
+	struct dc_reg_helper_state *offload = &ctx->dmub_srv->reg_helper_offload;
+	struct dmub_rb_cmd_reg_wait *cmd_buf = &offload->cmd_data.reg_wait;
+
+	cmd_buf->header.type = DMUB_CMD__REG_REG_WAIT;
+	cmd_buf->header.sub_type = 0;
+	cmd_buf->reg_wait.addr = addr;
+	cmd_buf->reg_wait.condition_field_value = mask & (condition_value << shift);
+	cmd_buf->reg_wait.mask = mask;
+	cmd_buf->reg_wait.time_out_us = time_out_us;
+}
+
+uint32_t generic_reg_update_ex(const struct dc_context *ctx,
+		uint32_t addr, int n,
+		uint8_t shift1, uint32_t mask1, uint32_t field_value1,
+		...)
+{
+	struct dc_reg_value_masks field_value_mask = {0};
+	uint32_t reg_val;
+	va_list ap;
+
+	va_start(ap, field_value1);
+
+	set_reg_field_values(&field_value_mask, addr, n, shift1, mask1,
+			field_value1, ap);
+
+	va_end(ap);
+
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress)
+		return dmub_reg_value_pack(ctx, addr, &field_value_mask);
+		/* todo: return void so we can decouple code running in driver from register states */
+
+	/* mmio write directly */
+	reg_val = dm_read_reg(ctx, addr);
+	reg_val = (reg_val & ~field_value_mask.mask) | field_value_mask.value;
+	dm_write_reg(ctx, addr, reg_val);
+	return reg_val;
+}
+
+uint32_t generic_reg_set_ex(const struct dc_context *ctx,
+		uint32_t addr, uint32_t reg_val, int n,
+		uint8_t shift1, uint32_t mask1, uint32_t field_value1,
+		...)
+{
+	struct dc_reg_value_masks field_value_mask = {0};
+	va_list ap;
+
+	va_start(ap, field_value1);
+
+	set_reg_field_values(&field_value_mask, addr, n, shift1, mask1,
+			field_value1, ap);
+
+	va_end(ap);
+
+
+	/* mmio write directly */
+	reg_val = (reg_val & ~field_value_mask.mask) | field_value_mask.value;
+
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress) {
+		return dmub_reg_value_burst_set_pack(ctx, addr, reg_val);
+		/* todo: return void so we can decouple code running in driver from register states */
+	}
+
+	dm_write_reg(ctx, addr, reg_val);
+	return reg_val;
+}
+
+uint32_t generic_reg_get(const struct dc_context *ctx, uint32_t addr,
+		uint8_t shift, uint32_t mask, uint32_t *field_value)
+{
+	uint32_t reg_val = dm_read_reg(ctx, addr);
+	*field_value = get_reg_field_value_ex(reg_val, mask, shift);
+	return reg_val;
+}
+
+uint32_t generic_reg_get2(const struct dc_context *ctx, uint32_t addr,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		uint8_t shift2, uint32_t mask2, uint32_t *field_value2)
+{
+	uint32_t reg_val = dm_read_reg(ctx, addr);
+	*field_value1 = get_reg_field_value_ex(reg_val, mask1, shift1);
+	*field_value2 = get_reg_field_value_ex(reg_val, mask2, shift2);
+	return reg_val;
+}
+
+uint32_t generic_reg_get3(const struct dc_context *ctx, uint32_t addr,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		uint8_t shift2, uint32_t mask2, uint32_t *field_value2,
+		uint8_t shift3, uint32_t mask3, uint32_t *field_value3)
+{
+	uint32_t reg_val = dm_read_reg(ctx, addr);
+	*field_value1 = get_reg_field_value_ex(reg_val, mask1, shift1);
+	*field_value2 = get_reg_field_value_ex(reg_val, mask2, shift2);
+	*field_value3 = get_reg_field_value_ex(reg_val, mask3, shift3);
+	return reg_val;
+}
+
+uint32_t generic_reg_get4(const struct dc_context *ctx, uint32_t addr,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		uint8_t shift2, uint32_t mask2, uint32_t *field_value2,
+		uint8_t shift3, uint32_t mask3, uint32_t *field_value3,
+		uint8_t shift4, uint32_t mask4, uint32_t *field_value4)
+{
+	uint32_t reg_val = dm_read_reg(ctx, addr);
+	*field_value1 = get_reg_field_value_ex(reg_val, mask1, shift1);
+	*field_value2 = get_reg_field_value_ex(reg_val, mask2, shift2);
+	*field_value3 = get_reg_field_value_ex(reg_val, mask3, shift3);
+	*field_value4 = get_reg_field_value_ex(reg_val, mask4, shift4);
+	return reg_val;
+}
+
+uint32_t generic_reg_get5(const struct dc_context *ctx, uint32_t addr,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		uint8_t shift2, uint32_t mask2, uint32_t *field_value2,
+		uint8_t shift3, uint32_t mask3, uint32_t *field_value3,
+		uint8_t shift4, uint32_t mask4, uint32_t *field_value4,
+		uint8_t shift5, uint32_t mask5, uint32_t *field_value5)
+{
+	uint32_t reg_val = dm_read_reg(ctx, addr);
+	*field_value1 = get_reg_field_value_ex(reg_val, mask1, shift1);
+	*field_value2 = get_reg_field_value_ex(reg_val, mask2, shift2);
+	*field_value3 = get_reg_field_value_ex(reg_val, mask3, shift3);
+	*field_value4 = get_reg_field_value_ex(reg_val, mask4, shift4);
+	*field_value5 = get_reg_field_value_ex(reg_val, mask5, shift5);
+	return reg_val;
+}
+
+uint32_t generic_reg_get6(const struct dc_context *ctx, uint32_t addr,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		uint8_t shift2, uint32_t mask2, uint32_t *field_value2,
+		uint8_t shift3, uint32_t mask3, uint32_t *field_value3,
+		uint8_t shift4, uint32_t mask4, uint32_t *field_value4,
+		uint8_t shift5, uint32_t mask5, uint32_t *field_value5,
+		uint8_t shift6, uint32_t mask6, uint32_t *field_value6)
+{
+	uint32_t reg_val = dm_read_reg(ctx, addr);
+	*field_value1 = get_reg_field_value_ex(reg_val, mask1, shift1);
+	*field_value2 = get_reg_field_value_ex(reg_val, mask2, shift2);
+	*field_value3 = get_reg_field_value_ex(reg_val, mask3, shift3);
+	*field_value4 = get_reg_field_value_ex(reg_val, mask4, shift4);
+	*field_value5 = get_reg_field_value_ex(reg_val, mask5, shift5);
+	*field_value6 = get_reg_field_value_ex(reg_val, mask6, shift6);
+	return reg_val;
+}
+
+uint32_t generic_reg_get7(const struct dc_context *ctx, uint32_t addr,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		uint8_t shift2, uint32_t mask2, uint32_t *field_value2,
+		uint8_t shift3, uint32_t mask3, uint32_t *field_value3,
+		uint8_t shift4, uint32_t mask4, uint32_t *field_value4,
+		uint8_t shift5, uint32_t mask5, uint32_t *field_value5,
+		uint8_t shift6, uint32_t mask6, uint32_t *field_value6,
+		uint8_t shift7, uint32_t mask7, uint32_t *field_value7)
+{
+	uint32_t reg_val = dm_read_reg(ctx, addr);
+	*field_value1 = get_reg_field_value_ex(reg_val, mask1, shift1);
+	*field_value2 = get_reg_field_value_ex(reg_val, mask2, shift2);
+	*field_value3 = get_reg_field_value_ex(reg_val, mask3, shift3);
+	*field_value4 = get_reg_field_value_ex(reg_val, mask4, shift4);
+	*field_value5 = get_reg_field_value_ex(reg_val, mask5, shift5);
+	*field_value6 = get_reg_field_value_ex(reg_val, mask6, shift6);
+	*field_value7 = get_reg_field_value_ex(reg_val, mask7, shift7);
+	return reg_val;
+}
+
+uint32_t generic_reg_get8(const struct dc_context *ctx, uint32_t addr,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		uint8_t shift2, uint32_t mask2, uint32_t *field_value2,
+		uint8_t shift3, uint32_t mask3, uint32_t *field_value3,
+		uint8_t shift4, uint32_t mask4, uint32_t *field_value4,
+		uint8_t shift5, uint32_t mask5, uint32_t *field_value5,
+		uint8_t shift6, uint32_t mask6, uint32_t *field_value6,
+		uint8_t shift7, uint32_t mask7, uint32_t *field_value7,
+		uint8_t shift8, uint32_t mask8, uint32_t *field_value8)
+{
+	uint32_t reg_val = dm_read_reg(ctx, addr);
+	*field_value1 = get_reg_field_value_ex(reg_val, mask1, shift1);
+	*field_value2 = get_reg_field_value_ex(reg_val, mask2, shift2);
+	*field_value3 = get_reg_field_value_ex(reg_val, mask3, shift3);
+	*field_value4 = get_reg_field_value_ex(reg_val, mask4, shift4);
+	*field_value5 = get_reg_field_value_ex(reg_val, mask5, shift5);
+	*field_value6 = get_reg_field_value_ex(reg_val, mask6, shift6);
+	*field_value7 = get_reg_field_value_ex(reg_val, mask7, shift7);
+	*field_value8 = get_reg_field_value_ex(reg_val, mask8, shift8);
+	return reg_val;
+}
+/* note:  va version of this is pretty bad idea, since there is a output parameter pass by pointer
+ * compiler won't be able to check for size match and is prone to stack corruption type of bugs
+
+uint32_t generic_reg_get(const struct dc_context *ctx,
+		uint32_t addr, int n, ...)
+{
+	uint32_t shift, mask;
+	uint32_t *field_value;
+	uint32_t reg_val;
+	int i = 0;
+
+	reg_val = dm_read_reg(ctx, addr);
+
+	va_list ap;
+	va_start(ap, n);
+
+	while (i < n) {
+		shift = va_arg(ap, uint32_t);
+		mask = va_arg(ap, uint32_t);
+		field_value = va_arg(ap, uint32_t *);
+
+		*field_value = get_reg_field_value_ex(reg_val, mask, shift);
+		i++;
+	}
+
+	va_end(ap);
+
+	return reg_val;
+}
+*/
+
+void generic_reg_wait(const struct dc_context *ctx,
+	uint32_t addr, uint32_t shift, uint32_t mask, uint32_t condition_value,
+	unsigned int delay_between_poll_us, unsigned int time_out_num_tries,
+	const char *func_name, int line)
+{
+	uint32_t field_value;
+	uint32_t reg_val;
+	int i;
+
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress) {
+		dmub_reg_wait_done_pack(ctx, addr, mask, shift, condition_value,
+				delay_between_poll_us * time_out_num_tries);
+		return;
+	}
+
+	/*
+	 * Something is terribly wrong if time out is > 3000ms.
+	 * 3000ms is the maximum time needed for SMU to pass values back.
+	 * This value comes from experiments.
+	 *
+	 */
+	ASSERT(delay_between_poll_us * time_out_num_tries <= 3000000);
+
+	for (i = 0; i <= time_out_num_tries; i++) {
+		if (i) {
+			if (delay_between_poll_us >= 1000)
+				msleep(delay_between_poll_us/1000);
+			else if (delay_between_poll_us > 0)
+				udelay(delay_between_poll_us);
+		}
+
+		reg_val = dm_read_reg(ctx, addr);
+
+		field_value = get_reg_field_value_ex(reg_val, mask, shift);
+
+		if (field_value == condition_value) {
+			if (i * delay_between_poll_us > 1000 &&
+					!IS_FPGA_MAXIMUS_DC(ctx->dce_environment))
+				DC_LOG_DC("REG_WAIT taking a while: %dms in %s line:%d\n",
+						delay_between_poll_us * i / 1000,
+						func_name, line);
+			return;
+		}
+	}
+
+	DC_LOG_WARNING("REG_WAIT timeout %dus * %d tries - %s line:%d\n",
+			delay_between_poll_us, time_out_num_tries,
+			func_name, line);
+
+	if (!IS_FPGA_MAXIMUS_DC(ctx->dce_environment))
+		BREAK_TO_DEBUGGER();
+}
+
+void generic_write_indirect_reg(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, uint32_t data)
+{
+	dm_write_reg(ctx, addr_index, index);
+	dm_write_reg(ctx, addr_data, data);
+}
+
+uint32_t generic_read_indirect_reg(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index)
+{
+	uint32_t value = 0;
+
+	// when reg read, there should not be any offload.
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress) {
+		ASSERT(false);
+	}
+
+	dm_write_reg(ctx, addr_index, index);
+	value = dm_read_reg(ctx, addr_data);
+
+	return value;
+}
+
+uint32_t generic_indirect_reg_get(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, int n,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		...)
+{
+	uint32_t shift, mask, *field_value;
+	uint32_t value = 0;
+	int i = 1;
+
+	va_list ap;
+
+	va_start(ap, field_value1);
+
+	value = generic_read_indirect_reg(ctx, addr_index, addr_data, index);
+	*field_value1 = get_reg_field_value_ex(value, mask1, shift1);
+
+	while (i < n) {
+		shift = va_arg(ap, uint32_t);
+		mask = va_arg(ap, uint32_t);
+		field_value = va_arg(ap, uint32_t *);
+
+		*field_value = get_reg_field_value_ex(value, mask, shift);
+		i++;
+	}
+
+	va_end(ap);
+
+	return value;
+}
+
+uint32_t generic_indirect_reg_update_ex(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, uint32_t reg_val, int n,
+		uint8_t shift1, uint32_t mask1, uint32_t field_value1,
+		...)
+{
+	uint32_t shift, mask, field_value;
+	int i = 1;
+
+	va_list ap;
+
+	va_start(ap, field_value1);
+
+	reg_val = set_reg_field_value_ex(reg_val, field_value1, mask1, shift1);
+
+	while (i < n) {
+		shift = va_arg(ap, uint32_t);
+		mask = va_arg(ap, uint32_t);
+		field_value = va_arg(ap, uint32_t);
+
+		reg_val = set_reg_field_value_ex(reg_val, field_value, mask, shift);
+		i++;
+	}
+
+	generic_write_indirect_reg(ctx, addr_index, addr_data, index, reg_val);
+	va_end(ap);
+
+	return reg_val;
+}
+
+
+uint32_t generic_indirect_reg_update_ex_sync(const struct dc_context *ctx,
+		uint32_t index, uint32_t reg_val, int n,
+		uint8_t shift1, uint32_t mask1, uint32_t field_value1,
+		...)
+{
+	uint32_t shift, mask, field_value;
+	int i = 1;
+
+	va_list ap;
+
+	va_start(ap, field_value1);
+
+	reg_val = set_reg_field_value_ex(reg_val, field_value1, mask1, shift1);
+
+	while (i < n) {
+		shift = va_arg(ap, uint32_t);
+		mask = va_arg(ap, uint32_t);
+		field_value = va_arg(ap, uint32_t);
+
+		reg_val = set_reg_field_value_ex(reg_val, field_value, mask, shift);
+		i++;
+	}
+
+	dm_write_index_reg(ctx, CGS_IND_REG__PCIE, index, reg_val);
+	va_end(ap);
+
+	return reg_val;
+}
+
+uint32_t generic_indirect_reg_get_sync(const struct dc_context *ctx,
+		uint32_t index, int n,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		...)
+{
+	uint32_t shift, mask, *field_value;
+	uint32_t value = 0;
+	int i = 1;
+
+	va_list ap;
+
+	va_start(ap, field_value1);
+
+	value = dm_read_index_reg(ctx, CGS_IND_REG__PCIE, index);
+	*field_value1 = get_reg_field_value_ex(value, mask1, shift1);
+
+	while (i < n) {
+		shift = va_arg(ap, uint32_t);
+		mask = va_arg(ap, uint32_t);
+		field_value = va_arg(ap, uint32_t *);
+
+		*field_value = get_reg_field_value_ex(value, mask, shift);
+		i++;
+	}
+
+	va_end(ap);
+
+	return value;
+}
+
+void reg_sequence_start_gather(const struct dc_context *ctx)
+{
+	/* if reg sequence is supported and enabled, set flag to
+	 * indicate we want to have REG_SET, REG_UPDATE macro build
+	 * reg sequence command buffer rather than MMIO directly.
+	 */
+
+	if (ctx->dmub_srv && ctx->dc->debug.dmub_offload_enabled) {
+		struct dc_reg_helper_state *offload =
+			&ctx->dmub_srv->reg_helper_offload;
+
+		/* caller sequence mismatch.  need to debug caller.  offload will not work!!! */
+		ASSERT(!offload->gather_in_progress);
+
+		offload->gather_in_progress = true;
+	}
+}
+
+void reg_sequence_start_execute(const struct dc_context *ctx)
+{
+	struct dc_reg_helper_state *offload;
+
+	if (!ctx->dmub_srv)
+		return;
+
+	offload = &ctx->dmub_srv->reg_helper_offload;
+
+	if (offload && offload->gather_in_progress) {
+		offload->gather_in_progress = false;
+		offload->should_burst_write = false;
+		switch (offload->cmd_data.cmd_common.header.type) {
+		case DMUB_CMD__REG_SEQ_READ_MODIFY_WRITE:
+			submit_dmub_read_modify_write(offload, ctx);
+			break;
+		case DMUB_CMD__REG_REG_WAIT:
+			submit_dmub_reg_wait(offload, ctx);
+			break;
+		case DMUB_CMD__REG_SEQ_BURST_WRITE:
+			submit_dmub_burst_write(offload, ctx);
+			break;
+		default:
+			return;
+		}
+
+		dc_dmub_srv_cmd_execute(ctx->dmub_srv);
+	}
+}
+
+void reg_sequence_wait_done(const struct dc_context *ctx)
+{
+	/* callback to DM to poll for last submission done*/
+	struct dc_reg_helper_state *offload;
+
+	if (!ctx->dmub_srv)
+		return;
+
+	offload = &ctx->dmub_srv->reg_helper_offload;
+
+	if (offload &&
+	    ctx->dc->debug.dmub_offload_enabled &&
+	    !ctx->dc->debug.dmcub_emulation) {
+		dc_dmub_srv_wait_idle(ctx->dmub_srv);
+	}
+}